Skip to main content
Glama
README.md
# sfxbrew

Procedural game sound effects for humans **and AI coding agents**. Eastern (wuxia / xianxia) sounds plus the usual game sounds, synthesized locally, with no API keys, no network and no per-call cost.

- 29 presets: sword qi, guqin, pipa, erhu, wooden fish, war drum, lightning, temple bell, gong, spell cast, heavenly thunder, breakthrough, talisman, alchemy, wind chime, bamboo flute, qi gathering, coin, pickup, click, confirm, error, jump, hit, explosion, laser, power-up, level up, whoosh
- Every generation is a fresh variation; a **seed** reproduces it exactly
- Output: 16-bit WAV, or a ~7 KB dependency-free JavaScript snippet that plays the same sound with Web Audio
- **Free for commercial use, no attribution required** for the sounds you generate

## For AI agents (MCP)

Claude Code:

```bash
claude mcp add sfxbrew -- npx -y sfxbrew mcp
```

Other MCP clients (Cursor, Windsurf, Claude Desktop …):

```json
{
  "mcpServers": {
    "sfxbrew": { "command": "npx", "args": ["-y", "sfxbrew", "mcp"] }
  }
}
```

Tools:

| Tool | What it does |
|---|---|
| `list_presets` | Presets and what each one is good for |
| `generate_sfx` | Write one or more WAV variants (and optionally a `.js` file with play functions) |
| `render_patch` | Render a hand-tuned patch JSON |
| `get_js_code` | One drop-in JS snippet with `playX()` functions for several sounds |

Then just ask: *"add a coin sound and a hit sound to my game"*.

## Agent skill

A free SKILL.md that teaches your agent when and how to use SFX Brew: [skills/sfxbrew/SKILL.md](skills/sfxbrew/SKILL.md), also installable from [Agensi](https://www.agensi.io/skills/sfx-brew-game-sound-effects).

## CLI

```bash
npx sfxbrew list
npx sfxbrew coin --out assets/sfx/coin.wav
npx sfxbrew swordQi --count 5 --out assets/sfx/sword.wav
npx sfxbrew hit --seed 42 --js src/sfx.js
npx sfxbrew render my-patch.json --out boom.wav
```

## Sound packs

Ready-made WAV packs: [Xianxia & Wuxia Game Sound Pack on itch.io](https://2365836149-sketch.itch.io/xianxia-wuxia-sound-pack) (44 sounds), or download any pack as a ZIP from [sfxbrew.com/sounds](https://sfxbrew.com/sounds/).

## Library

```js
const sfx = require('sfxbrew');
const { patch, seed } = sfx.generate('coin');
const { bytes } = await sfx.renderWav(patch);
```

## Browser editor

Tweak any sound with sliders and export WAV / JS in the [web editor](https://sfxbrew.com/) (same engine).

## License

Code: MIT. Generated sounds: yours, free for any use.

A few presets (war drum, lightning, gong, erhu) use short CC0 recordings from Freesound, listed with their recordists in [samples/CREDITS.md](samples/CREDITS.md).

TDQS

A4.2/5.0

Scored across 4 tools

Disambiguation4/5

Each tool has a clear role in the pipeline: discover presets, synthesize from a preset, render a hand-edited patch, and export browser JS. The only mild overlap is that generate_sfx and render_patch both output WAV files, but their inputs (preset vs. patch JSON) and intended stages are clearly distinguished.

Naming Consistency5/5

All four names follow a clean verb_noun snake_case pattern: list_presets, generate_sfx, render_patch, get_js_code. The convention is predictable and readable.

Tool Count5/5

Four tools is compact and well-scoped for a procedural SFX generator, and each tool earns its place in a coherent discover → generate → fine-tune → export workflow. Nothing feels redundant or missing at the count level.

Completeness4/5

The core lifecycle is covered: browsing presets, generating variants with seeds, editing patch JSON for fine-tuning, and exporting playable JS snippets. Minor gaps remain, such as no audio preview/playback tool and no way to list, manage, or delete previously generated files.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues